CN106682802A - Post value estimation method and system - Google Patents
Post value estimation method and system Download PDFInfo
- Publication number
- CN106682802A CN106682802A CN201510760266.0A CN201510760266A CN106682802A CN 106682802 A CN106682802 A CN 106682802A CN 201510760266 A CN201510760266 A CN 201510760266A CN 106682802 A CN106682802 A CN 106682802A
- Authority
- CN
- China
- Prior art keywords
- variable
- value
- valuation
- salary
- post
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Landscapes
- Financial Or Insurance-Related Operations Such As Payment And Settlement (AREA)
Abstract
The invention provides a post value estimation method and a system. The method comprises the following steps: defining a post value estimation variable and a future value-adding variable for a plurality of existing posts possibly to be occupied through job transfers wherein the post value estimation variable is defined as the sum of the post salary and the future value-adding variable; obtaining the transfer probability of each post to be transferred to other posts or to stay unchanged on the original post; calculating the determined value of the post value estimation variable of each post according to the preset correlated relationship between future value-adding variable of each post and the post value estimation variable of other posts wherein the correlated relationship comprises: obtaining the difference in the post value estimation between one current post and other posts; using the difference as a preset variable; using the transfer probability of the current post to other posts as the weight of the preset variable, and according to the calculated weight sum as the future value-adding variable of the current post. The vocational value estimation schemes proposed by the invention consider the matching of the salary and professional skills as well as the various paths of vocational development, enabling the schemes to be of highly reference value. The method and the system can also be of great commercial value.
Description
Technical field
The present invention relates to software systems technological system, more particularly to position estimation method and system.
Background technology
With the development of internet, recruitment mode in internet will become the main channel of employment from now on.It is existing
The target of internet recruitment website be to reach the transaction of employment as much as possible, the major technique taken and flow process point
For following three part：
1) resume of job hunter is collected, biographic information database is built；
2) position vacant information is collected, builds job database；
3) by the keyword in resume and job information, the matching between resume and position vacant is carried out.
Existing internet recruitment website cannot effectively meet demand of the job hunter for occupational planning, and reason has following several
Kind：
1) job database of each recruitment website and job seeker tip's database are the own databases of each recruitment website,
And separate between recruitment website database, mutually closing.Job hunter one-stop cannot understand all career development path letters
The possibility of breath；
2) technology for matching keyword in job information and biographic information reflects position demand and job hunter's self-ability
Similarity, but only show that job hunter applies for the possibility of this kind of position, it is impossible to the index excellent as position is passed judgment on, for example
Some positions most like with job hunter's ability actually lack future growth space, are unfavorable for the long term growth of job hunter；
3) position valuation computational methods disappearance.It is to be based on salary that existing recruitment website carry out the sequence of position value to calculate,
And salary only reflects the short-period value of certain position, and the increasing to job hunter's long term growth brought not comprising this position
Value.
The content of the invention
The shortcoming of prior art in view of the above, it is an object of the invention to provide position estimation method and system, use
In solving the problems, such as that job information content is single unilateral provided in prior art.
For achieving the above object and other related purposes, the present invention provides a kind of position estimation method, including：To there is phase
Possible multiple positions of mutually job-hoping define position valuation variable and following increment variable, and the position valuation variable-definition is
The salary value of the position and following increment variable and；Each position described in obtaining to other each positions job-hoppings or stays in original respectively
The transition probability of position；By the position valuation variable association relation of the following increment variable of default each position and other positions come
The determination value of the position valuation variable of each position is calculated, wherein, the incidence relation includes：Obtain a current position with
The difference of the position valuation variable of each position is made with current position as design variables to the transition probability of each position
For the weighted value of the design variables, and using the weighted sum for calculating according to this as the current position following increment variable.
It is described by following variable and the position of other positions of rising in value of default each position in one embodiment of the invention
Valuation variable association relation being calculated the determination value of the position valuation variable of each position, including：Select an initial n dimensions
Vectorial V (n) is representing the position valuation variable of n position；The V (n) is iterated to calculate according to the incidence relation；Judge V
N ()-V (n-1) then proves stable states of the V (n) already close to convergence whether less than admissible error is allowed, if so, so as to calculate
Position valuation variable position valuation variable at steady state.
In one embodiment of the invention, described position estimation method also includes：From network collection recruitment information, with
Therefrom extract the information of each position and salary value；And/or, from network collection biographic information, therefrom to extract individual
Career development routing information.
In one embodiment of the invention, the salary value is by associating meter according to the true salary value of each position
Calculation mode calculates the relative salary value of acquisition.
In one embodiment of the invention, the acquisition modes of the transition probability value include：From gathered recruitment information
Extract related position skill set requirements；The similarity that the position skill set requirements between each position are obtained by comparing is used as transition probability
One of basis of value；And/or, to extracting career development path letter in the network collection biographic information of gathered crowd
Breath carries out the statistics of transfer case between position, using statistics as the transition probability value one of basis.
For achieving the above object and other related purposes, the present invention provides a kind of position valuation system, including：System is defined
Module for defining position valuation variable and following increment variable and described to there are the possible multiple positions of mutual job-hopping
Position valuation variable-definition be salary value and the following increment variable of the position and；Probability acquisition module, it is described for obtaining
Each position to other each positions job-hoppings or stays in the transition probability of former post position respectively；Valuation computing module, for by default
The following increment variable of each position and other positions position valuation variable association relation being calculated the position of each position
The determination value of valuation variable, wherein, the incidence relation includes：Obtain a current position to become with the position valuation of each position
The difference of amount as design variables, and using current position to the transition probability of each position as the weighted value of the design variables,
And using the weighted sum for calculating according to this as the current position following increment variable.
In one embodiment of the invention, the valuation computing module by the following increment variable of default each position and
The position valuation variable association relation of other positions being calculated the determination value of the position valuation variable of each position, including：
Select initial n-dimensional vector V (n) to represent the position valuation variable of n position；Institute is iterated to calculate according to the incidence relation
State V (n)；Whether V (n)-V (n-1) is judged less than admissible error is allowed, if so, then prove V (n) stablizing already close to convergence
State, so as to calculate position valuation variable position valuation variable at steady state.
In one embodiment of the invention, described position valuation system also includes：Information acquisition module, for from net
Network gathers recruitment information, therefrom to extract the information of each position and salary value；And/or, for from network collection letter
Information is gone through, therefrom to extract the career development routing information of individual.
In one embodiment of the invention, the salary value is by associating meter according to the true salary value of each position
Calculation mode calculates the relative salary value of acquisition.
In one embodiment of the invention, the probability acquisition module obtains the mode of the transition probability value to be included：From
Related position skill set requirements are extracted in gathered recruitment information；The phase of the position skill set requirements between each position is obtained by comparing
Like one of basis spent as transition probability value；And/or, to carrying in the network collection biographic information of gathered crowd
Taking career development routing information carries out the statistics of transfer case between position, using statistics as the transition probability value calculating
One of according to.
As described above, the position estimation method and system of the present invention, fixed to there are the possible multiple positions of mutual job-hopping
Adopted position valuation variable and following increment variable, and the position valuation variable-definition is the salary value of the position and following increment
The sum of variable；Obtain described each position and to other each positions job-hoppings or stay in the transition probability of former post position respectively；By default
The following increment variable of each position and other positions position valuation variable association relation being calculated the position of each position
The determination value of valuation variable, wherein, the incidence relation includes：Obtain a current position to become with the position valuation of each position
The difference of amount as design variables, and using current position to the transition probability of each position as the weighted value of the design variables,
And using the weighted sum for calculating according to this as the current position following increment variable.
The position valuation computational methods of the present invention have broken the limitation of existing recruitment instrument and algorithm, and have incorporated user and exist
Growth in position and all of career development routing information that thus position may be brought, based on real data and professional road
Footpath is analyzed, and professional value calculation is deduced, different from simple position matching primitives method, technical scheme
User's occupational planning of more fitting reality, it is contemplated that the true value of position, the current salary and not of position should be included
The growing space come, by technical scheme, people can give a true value simultaneously for each in job hunting position
The screening and sequence of optimum position are carried out accordingly.
The position valuation computational methods of the present invention are the figure calculating methods based on position development path and position relational network, because
And, for the calculating of position valuation accurately covers the path of all possible position development and possibility；User will no longer office
It is limited to oneself career development of the limited experience to oneself to plan.
Also, based on the position estimation algorithm of the present invention, coordinate existing vocational match algorithm, just can sort for user
Filter out and most match and fit well on actual position and future development program.
Description of the drawings
Fig. 1 is shown as the schematic flow sheet of position estimation method of the present invention in an embodiment.
Fig. 2 is shown as the Computing Principle schematic diagram of present invention position valuation in an embodiment.
Fig. 3 is shown as the module diagram of position valuation system of the present invention in an embodiment.
Fig. 4 is shown as on the basis of Fig. 2 embodiments the schematic diagram of the specific embodiment for carrying out parameter assignment.
Fig. 5 a and 5b are shown as the schematic diagram of multiple concrete application embodiments of the present invention.
Component label instructions
1 position valuation system
11 system definition modules
12 probability acquisition modules
13 valuation computing modules
S1～S3 steps
Specific embodiment
Embodiments of the present invention are illustrated below by way of specific instantiation, those skilled in the art can be by this specification
Disclosed content understands easily other advantages and effect of the present invention.The present invention can also pass through concrete realities different in addition
The mode of applying is carried out or applies, the every details in this specification can also based on different viewpoints with application, without departing from
Various modifications and changes are carried out under the spirit of the present invention.It should be noted that, in the case where not conflicting, following examples and enforcement
Feature in example can be mutually combined.
It should be noted that the diagram provided in following examples only illustrates in a schematic way the basic structure of the present invention
Think, only show in schema then with relevant component in the present invention rather than according to component count during actual enforcement, shape and size
Draw, it is actual when the implementing kenel of each component, quantity and ratio can be a kind of random change, and its assembly layout kenel
It is likely more complexity.
Fig. 1 is referred to, the present invention provides a kind of position estimation method, including：
Step S1：Position valuation variable, and the position valuation are defined to there are the possible multiple positions of mutual job-hopping
Variable-definition be salary value and the following increment variable of the position and；
Step S2：Obtain described each position and to other each positions job-hoppings or stay in the transition probability of former post position respectively；
Step S3：By the position valuation variable association relation of the following increment variable of default each position and other positions come
The determination value of the position valuation variable of each position is calculated, wherein, the incidence relation includes：Obtain a current position with
The difference of the position valuation variable of each position is made with current position as design variables to the transition probability of each position
For the weighted value of the design variables, and using the weighted sum for calculating according to this as the current position following increment variable.
The principle of said method is illustrated, in order to calculate a reasonable approximation to a position；The calculating of position valuation
Define following three formula：
Position valuation=current salary+future increment (1a)
Following increment=∑It is possible to promote the position of (job-hopping)Promote (job-hopping) probability × promotion (job-hopping) increment (1b)
∑It is possible to promote the position of (job-hopping)Promote (job-hopping) probability=1 (1c)
Wherein, " Σ " represents summation symbol；Future increment refers to that after the work of objective, future exists job hunter
The increment that the position or other positions are obtained；In one embodiment, the following increment of a position is sent out in be possible to position
Weighted average on exhibition path, future increment is the judging quota of the recessive value of each position, is also supplied to job hunting simultaneously
One foundation of the long-range occupational planning of person.
Fig. 2 shows a position graph of a relation, it is assumed that the position network of personal connections built by 3 positions, wherein, A, B, C is represented
Three kinds of associated positions, each other presence job-hopping is possible, constitutes various possible career development routing informations, i.e. occupation
Between shift path.
By taking position A as an example：
S1The salary of the existing offer of=A positions
ΔV1=available position the increment after A positions obtain from the off enough empirical values and ability
V1The true value of=A positions
According to position valuation computing formula (1a), the actually valuation of A positions is V1=S1+ΔV1。
By that analogy, the valuation of B positions is V2, the valuation of C positions is V3, then：
Position B：Salary S2, future increment is Δ V2, valuation is V3=S3+ΔV3；
Position C：Salary S3, future increment is Δ V3, valuation is V3=S3+ΔV3。
The relation for describing as illustrated, possesses at present the possible next step position choosing of the people of A positions ability to work and experience
Select 3 kinds of possibilities (to continue to stay in A positions；Job-hop to B positions；Job-hop to C positions), then the probability of position transfer just has two
Part constitutes：The probability summation of other positions of job-hopping, and the probability for staying in former post position；Job-hopping probability size depend on from
Former post position is cross over the increment that other positions are brought and the cost paid：
P11=continue to stay in the probability of A positions；
P12=job-hop to the probability of B positions；
P13=job-hop to the probability of C positions；
Wherein, had according to formula (1c)：
P11+P12+P13=1
According to formula (1b), the position increment Δ V of A positions1Can be drawn by following computing formula：
ΔV1=P11(V1-V1)+P12(V2-V1)+P13(V3-V1)
=P11V1+P12V2+P13V3-(P11+P12+P13)V1
=P11V1+P12V2+P13V3-V1
N dimensions are extended to according to the example above, it is known that：The current salary of position (i) is Si, future may rise in value as Δ Vi,
It is P from position (i) application to the possibility of position (j)ij；I, j are any 2 positions in n position.
Calculate according to aforementioned position formula, can calculate and draw：
Vi=Si+ΔVi(i=1 ..., n) (2a)
Formula (2a), (2b) are abbreviated as with vector representation：
V=S+ Δ V (3a)
Δ V=PV-V (3b)
Merge formula (3a), (3b) to draw：
For solution formula (4), an initial vector V is selected(0), the continuous iteration product in right is gone down, here, iteration n times
Result afterwards is
It is preferred, but not necessary, that to judge | | V(N)-V(N-1)| | whether it is condition less than admissible error, if less than, it was demonstrated that
V can obtain stable solution V already close to the stable state of convergence；If being not less than, continue to iterate to calculate.
From the foregoing, the salary value of transition probability value and position be definite value, its acquisition modes such as described below：
In one embodiment, with regard to the acquisition of the salary value, by gathering and each big recruitment website can be integrated and is known
In the generation of the recruitment homepage of name enterprise, seeks job information (comprising salary, the Back ground Information such as position responsibility and requirement)；Preferably, it is just
Salary value in calculating, above-mentioned formula can be calculated by association calculation according to the true salary value of each position
The relative salary value for obtaining, such as same set point value of true salary value (such as highest in each true salary value of each position
Salary value) ratio, specifically, such as the true salary of position 1 is 2000, and the true salary of position 2 is 3000, in each position most
High true salary is 5000, then the relative salary value of position 1 is 0.4, and the relative salary value of position 2 is 0.6.
In one embodiment, include with regard to the acquisition modes of the transition probability value：(1) carry from gathered recruitment information
Take related position skill set requirements；The similarity that the position skill set requirements between each position are obtained by comparing is used as transition probability value
One of basis, in the case that position skill set requirements are more similar, then it is believed that transition probability value is higher, otherwise, then it is assumed that
Transition probability value is lower, because transition probability value and the probable value sum for staying in former post position are 100%, therefore obtains transition probability
Value is equal to and obtains the probable value for staying in former post position；(2) send out extracting occupation in the network collection biographic information of gathered crowd
Exhibition routing information carries out the statistics of transfer case between position, using statistics as the transition probability value basis it
One, for example, in 5 people, there are 3 people to job-hop to B positions from A positions, and other two people jumps to C positions etc. from A positions, so
The information to Demographics can act also as transition probability value calculating foundation；The specific rules of above-mentioned calculation can be voluntarily
Setting is tested in setting, is not further repeated herein；Also, the two ways can be used in conjunction with as acquisition transition probability
The foundation of value, it is also possible to be used alone to obtain the transition probability value.
It is further preferred that the similarity of the position skill set requirements can be carried out according to the job information of aforementioned collection
Word, semantics recognition are calculated after comparing again；To support to carry out the comparison, position technical ability dictionary can be set up, will be adopted
Various near synonym, synonyms for the description of position technical ability of collection etc. sort out placement, and the similarity between definable word and word
Key element, for calculating the similarity.
It is corresponding with said method embodiment, as shown in figure 3, the present invention provides a kind of position valuation system 1, due to it
Principle is roughly the same with methods described embodiment, and it is no longer repeated for thus like ins and outs；The system 1 includes：System
System definition module 11, for defining position valuation variable to there are the possible multiple positions of mutual job-hopping, and the position is estimated
Value variable-definition be salary value and the following increment variable of the position and；Probability acquisition module 12, for obtain it is described each
Position to other each positions job-hoppings or stays in the transition probability of former post position respectively；Valuation computing module 13, for by default
The position valuation variable association relation of the following increment variable of each position and other positions is estimated come the position for being calculated each position
The determination value of value variable, wherein, the incidence relation includes：Obtain the position valuation variable of a current position and each position
Difference as design variables, and using current position to the transition probability of each position as the weighted value of the design variables, and
Using the weighted sum for calculating according to this as the current position following increment variable.
In one embodiment of the invention, the valuation computing module 13 by the following increment variable of default each position
The determination value of the position valuation variable of each position is calculated with the position valuation variable association relation of other positions, is wrapped
Include：Select initial n-dimensional vector V (n) to represent the position valuation variable of n position；According to the incidence relation iteration meter
Calculate the V (n)；Whether V (n)-V (n-1) is judged less than admissible error is allowed, if so, then prove V (n) already close to convergence
Stable state, so as to calculate position valuation variable position valuation variable at steady state.
In one embodiment of the invention, described position valuation system 1 also includes：Information acquisition module, for from net
Network gathers recruitment information, therefrom to extract the information of each position and salary value；And/or, for from network collection letter
Information is gone through, therefrom to extract the career development routing information of individual.
In one embodiment of the invention, the salary value is by associating meter according to the true salary value of each position
Calculation mode calculates the relative salary value of acquisition.
In one embodiment of the invention, the probability acquisition module 12 obtains the mode of the transition probability value to be included：
Related position skill set requirements are extracted from gathered recruitment information；Position skill set requirements between each position are obtained by comparing
Basis one of of the similarity as transition probability value；And/or, in the network collection biographic information of gathered crowd
Extracting career development routing information carries out the statistics of transfer case between position, using statistics as the transition probability value meter
Calculate one of foundation.
Hereinafter the application of the instantiation explanation present invention is lifted again：
Fig. 4 is referred to, in order to preferably illustrate the difference of position valuation and position salary, there is provided be in Fig. 1 embodiments
On the basis of the example that calculates after concrete assignment is carried out to the salary S and transition probability P of each position；
Concrete assignment content is as follows：
Possessing the people of position ability and working experience needed for position A has P11=10% possibility continues to remain in office position A, has
P12=70% possibility changes to position B, there is P13=20% possibility changes to position C；
Possessing the people of position ability and working experience needed for position B has P22=80% possibility continues to remain in office position B, has
P23=20% possibility changes to position C；
Possessing the people of position ability and working experience needed for position C has P33=50% possibility continues to remain in office position C, has
P31=40% possibility changes to position A, there is P32=10% possibility changes to position B；
The relative salary i of three kinds of positions is respectively S1=0.6, S2=1, S3=0.7.
So, according to formula (2a) and (2b),
V1=S1+ΔV1=0.6+0.1V1+0.7V2+0.2V3-V1
V2=S2+ΔV2=1+0.8V2+0.2V3-V2
V3=S3+ΔV3=0.7+0.4V1+0.1V2+0.5V3-V3
Simultaneous above equation group can be obtained：
V1=0.744
V2=0.955
V3=0.729
According to above-mentioned position estimation algorithm, position A>Position C (sorts) according to position valuation
But if only position value is weighed by salary according to existing, then position C>Position A (is arranged according to salary value
Sequence), therefore, the valuation result obtained by the position valuation mode of the present invention is more had than existing position valuation mode
Reference value.
It should be noted that, said method embodiment or system can be realized by software, be applied to such as website or software visitor
Family end etc., such as shown in Fig. 5 a, show using such as recruitment website of technical solution of the present invention, by the technical side of the present invention
Case coordinates existing network technology to represent in html webpage；Again or as shown in Figure 5 b, for example, by smart mobile phone, flat board
The APP application programs realization that the mobile terminals such as computer are loaded, therefore, technical scheme can be applicable to various internets
Network, electric terminal etc., the commercial value with height.
In sum, position estimation method of the invention and system, it is fixed to there are the possible multiple positions of mutual job-hopping
Adopted position valuation variable and following increment variable, and the position valuation variable-definition is the salary value of the position and following increment
The sum of variable；Obtain described each position and to other each positions job-hoppings or stay in the transition probability of former post position respectively；By default
The following increment variable of each position and other positions position valuation variable association relation being calculated the position of each position
The determination value of valuation variable, wherein, the incidence relation includes：Obtain a current position to become with the position valuation of each position
The difference of amount as design variables, and using current position to the transition probability of each position as the weighted value of the design variables,
And using the weighted sum for calculating according to this as the current position following increment variable.
The position valuation computational methods of the present invention have broken the limitation of existing recruitment instrument and algorithm, and have incorporated user and exist
Growth in position and all of career development routing information that thus position may be brought, based on real data and professional road
Footpath is analyzed, and professional value calculation is deduced, different from simple position matching primitives method, technical scheme
User's occupational planning of more fitting reality, it is contemplated that the true value of position, the current salary and not of position should be included
The growing space come, by technical scheme, people can give a true value simultaneously for each in job hunting position
The screening and sequence of optimum position are carried out accordingly.
The position valuation computational methods of the present invention are the figure calculating methods based on position development path and position relational network, because
And, for the calculating of position valuation accurately covers the path of all possible position development and possibility；User will no longer office
It is limited to oneself career development of the limited experience to oneself to plan.
Also, based on the position estimation algorithm of the present invention, coordinate existing vocational match algorithm, just can sort for user
Filter out and most match and fit well on actual position and future development program.
The present invention effectively overcomes various shortcoming of the prior art and has high industrial utilization.
The principle and its effect of above-described embodiment only illustrative present invention, it is of the invention not for limiting.It is any ripe
Know the personage of this technology all can carry out modifications and changes under the spirit and the scope without prejudice to the present invention to above-described embodiment.Cause
This, such as those of ordinary skill in the art is complete with institute under technological thought without departing from disclosed spirit
Into all equivalent modifications or change, should by the present invention claim be covered.
Claims (10)
1. a kind of position estimation method, it is characterised in that include：
Position valuation variable and following increment variable are defined to there are the possible multiple positions of mutual job-hopping, and the position is estimated
Value variable-definition be salary value and the following increment variable of the position and；
Obtain described each position and to other each positions job-hoppings or stay in the transition probability of former post position respectively；
It is calculated by the position valuation variable association relation of the default following increment variable of each position and other positions each
The determination value of the position valuation variable of individual position, wherein, the incidence relation includes：A current position is obtained with each position
Position valuation variable difference as design variables, and using current position to the transition probability of each position as the default change
The weighted value of amount, and using the weighted sum for calculating according to this as the current position following increment variable.
2. position estimation method according to claim 1, it is characterised in that described by the following increment of default each position
Variable is calculated the determination value of the position valuation variable of each position with the position valuation variable association relation of other positions,
Including：
Select initial n-dimensional vector V (n) to represent the position valuation variable of n position；
The V (n) is iterated to calculate according to the incidence relation；
Judge that V (n)-V (n-1), whether less than admissible error, if so, then proves stable states of the V (n) already close to convergence, from
And calculate position valuation variable position valuation variable at steady state.
3. position estimation method according to claim 1, it is characterised in that also include：From network collection recruitment information, with
Therefrom extract the information of each position and salary value；And/or, from network collection biographic information, therefrom to extract individual
Career development routing information.
4. the position estimation method according to claim 1 or 3, it is characterised in that the salary value is reported according to each
The true salary value of position calculates the relative salary value for obtaining by association calculation.
5. position estimation method according to claim 3, it is characterised in that the acquisition modes bag of the transition probability value
Include：
Related position skill set requirements are extracted from gathered recruitment information；The position technical ability obtained by comparing between each position will
Basis one of of the similarity asked as transition probability value；
And/or, carry out between position extracting career development routing information in the network collection biographic information of gathered crowd
The statistics of transfer case, using statistics as the transition probability value one of basis.
6. a kind of position valuation system, it is characterised in that include：
System definition module, for defining position valuation variable and following increment to there are the possible multiple positions of mutual job-hopping
Variable, and the position valuation variable-definition be salary value and the following increment variable of the position and；
Probability acquisition module, for obtain described each position respectively to other each positions job-hoppings or stay in former post position transfer it is general
Rate；
Valuation computing module, for by the position valuation variable association of the default following increment variable of each position and other positions
Relation being calculated the determination value of the position valuation variable of each position, wherein, the incidence relation includes：Obtain one current
The difference of the position valuation variable of position and each position as design variables, and with transfer from current position to each position
Probability and becomes as the weighted value of the design variables using the weighted sum for calculating according to this as the following increment of the current position
Amount.
7. position valuation system according to claim 6, it is characterised in that the valuation computing module by default
The position valuation variable association relation of the following increment variable of each position and other positions is estimated come the position for being calculated each position
The determination value of value variable, including：
Select initial n-dimensional vector V (n) to represent the position valuation variable of n position；
The V (n) is iterated to calculate according to the incidence relation；
Judge that V (n)-V (n-1), whether less than admissible error, if so, then proves stable states of the V (n) already close to convergence, from
And calculate position valuation variable position valuation variable at steady state.
8. position valuation system according to claim 6, it is characterised in that also include：Information acquisition module, for from net
Network gathers recruitment information, therefrom to extract the information of each position and salary value；And/or, for from network collection letter
Information is gone through, therefrom to extract the career development routing information of individual.
9. the position valuation system according to claim 6 or 8, it is characterised in that the salary value is reported according to each
The true salary value of position calculates the relative salary value for obtaining by association calculation.
10. position valuation system according to claim 8, it is characterised in that the probability acquisition module obtains described turning
Moving the mode of probable value includes：
Related position skill set requirements are extracted from gathered recruitment information；The position technical ability obtained by comparing between each position will
Basis one of of the similarity asked as transition probability value；
And/or, carry out between position extracting career development routing information in the network collection biographic information of gathered crowd
The statistics of transfer case, using statistics as the transition probability value one of basis.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510760266.0A CN106682802A (en) | 2015-11-10 | 2015-11-10 | Post value estimation method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510760266.0A CN106682802A (en) | 2015-11-10 | 2015-11-10 | Post value estimation method and system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN106682802A true CN106682802A (en) | 2017-05-17 |
Family
ID=58863654
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510760266.0A Pending CN106682802A (en) | 2015-11-10 | 2015-11-10 | Post value estimation method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106682802A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US11188834B1 (en) * | 2016-10-31 | 2021-11-30 | Microsoft Technology Licensing, Llc | Machine learning technique for recommendation of courses in a social networking service based on confidential data |
| CN115526590A (en) * | 2022-09-16 | 2022-12-27 | 深圳今日人才信息科技有限公司 | Efficient human-sentry matching and re-pushing method combining expert knowledge and algorithm |
-
2015
- 2015-11-10 CN CN201510760266.0A patent/CN106682802A/en active Pending
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US11188834B1 (en) * | 2016-10-31 | 2021-11-30 | Microsoft Technology Licensing, Llc | Machine learning technique for recommendation of courses in a social networking service based on confidential data |
| CN115526590A (en) * | 2022-09-16 | 2022-12-27 | 深圳今日人才信息科技有限公司 | Efficient human-sentry matching and re-pushing method combining expert knowledge and algorithm |
| CN115526590B (en) * | 2022-09-16 | 2023-08-04 | 深圳今日人才信息科技有限公司 | Efficient person post matching and re-pushing method combining expert knowledge and algorithm |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN103714084B (en) | The method and apparatus of recommendation information | |
| US9870408B2 (en) | Search method and system | |
| CN109934619A (en) | User's portrait tag modeling method, apparatus, electronic equipment and readable storage medium storing program for executing | |
| CN109360097A (en) | Prediction of Stock Index method, apparatus, equipment and storage medium based on deep learning | |
| CN111723292B (en) | Recommendation method, system, electronic equipment and storage medium based on graph neural network | |
| CN110532417A (en) | Image search method, device and terminal device based on depth Hash | |
| CN103744849A (en) | Method and device for automatic recommendation application | |
| CN108287864A (en) | A kind of interest group division methods, device, medium and computing device | |
| CN107391582B (en) | The information recommendation method of user preference similarity is calculated based on context ontology tree | |
| CN110033331A (en) | Method, system and terminal device for issuing coupons | |
| CN103559252A (en) | Method for recommending scenery spots probably browsed by tourists | |
| CN103034687B (en) | A kind of relating module recognition methodss based on 2 class heterogeneous networks | |
| CN109101938A (en) | A kind of multi-tag age estimation method based on convolutional neural networks | |
| CN108664515A (en) | A kind of searching method and device, electronic equipment | |
| CN109582849A (en) | A kind of Internet resources intelligent search method of knowledge based map | |
| CN109117742A (en) | Gestures detection model treatment method, apparatus, equipment and storage medium | |
| CN110147389A (en) | Account number treating method and apparatus, storage medium and electronic device | |
| CN110852785B (en) | User grading method, device and computer readable storage medium | |
| CN107656918B (en) | Obtain the method and device of target user | |
| CN112785005A (en) | Multi-target task assistant decision-making method and device, computer equipment and medium | |
| CN109885651A (en) | A kind of question pushing method and device | |
| CN114881712B (en) | Intelligent advertisement putting method, device, equipment and storage medium | |
| CN109978575A (en) | A kind of method and device excavated customer flow and manage scene | |
| CN103218419B (en) | Web tab clustering method and system | |
| CN108770002A (en) | Base station flow analysis method, device, equipment and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20170517 |